Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Difficult tasks/processes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hunting
    -0.06
     †
    -0.06
     overse
    -0.06
     가격
    -0.06
    _logout
    -0.06
     knack
    -0.06
    股份
    -0.06
     polarization
    -0.06
    DIR
    -0.06
    urnal
    -0.06
    POSITIVE LOGITS
    rary
    0.07
    Showing
    0.07
     мот
    0.06
    ΕΥ
    0.06
     spokesperson
    0.06
    Kom
    0.06
     رفع
    0.06
     drummer
    0.06
    іх
    0.06
    angelo
    0.06
    Act Density 0.029%

    No Known Activations